Visual Odometry Revisited: What Should Be Learnt?

09/21/2019
by   Huangying Zhan, et al.
0

In this work we present a monocular visual odometry (VO) algorithm which leverages geometry-based methods and deep learning. Most existing VO/SLAM systems with superior performance are based on geometry and have to be carefully designed for different application scenarios. Moreover, most monocular systems suffer from scale-drift issue. Some recent deep learning works learn VO in an end-to-end manner but the performance of these deep systems is still not comparable to geometry-based methods. In this work, we revisit the basics of VO and explore the right way for integrating deep learning with epipolar geometry and Perspective-n-Point (PnP) method. Specifically, we train two convolutional neural networks (CNNs) for estimating single-view depths and two-view optical flows as intermediate outputs. With the deep predictions, we design a simple but robust frame-to-frame VO algorithm (DF-VO) which outperforms pure deep learning-based and geometry-based methods. More importantly, our system does not suffer from the scale-drift issue being aided by a scale consistent single-view depth CNN. Extensive experiments on KITTI dataset shows the robustness of our system and a detailed ablation study shows the effect of different factors in our system.

READ FULL TEXT
research
03/01/2021

DF-VO: What Should Be Learnt for Visual Odometry?

Multi-view geometry-based methods dominate the last few decades in monoc...
research
07/27/2020

WGANVO: Monocular Visual Odometry based on Generative Adversarial Networks

In this work we present WGANVO, a Deep Learning based monocular Visual O...
research
03/11/2018

Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction

Despite learning based methods showing promising results in single view ...
research
09/25/2017

DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks

This paper studies monocular visual odometry (VO) problem. Most of exist...
research
03/25/2019

Learning Monocular Visual Odometry through Geometry-Aware Curriculum Learning

Inspired by the cognitive process of humans and animals, Curriculum Lear...
research
03/18/2021

Deep Online Correction for Monocular Visual Odometry

In this work, we propose a novel deep online correction (DOC) framework ...
research
09/21/2021

Scale-aware direct monocular odometry

We present a framework for direct monocular odometry based on depth pred...

Please sign up or login with your details

Forgot password? Click here to reset